vwxyzjn's picture
Update README.md
82f4a71 verified
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - HuggingFaceH4/cai-conversation-harmless
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: mistral-7b-sft-constitutional-ai
    results: []

mistral-7b-sft-constitutional-ai

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/cai-conversation-harmless and the HuggingFaceH4/ultrachat_200k datasets. It achieves the following results on the evaluation set:

  • Loss: 0.9344

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.9241 1.0 550 0.9344

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.1